trace_synthesis/tasks/7.json
yuyr a84d51a101 1. 增加r1生成综合策略代码和输出;
2. 增加tasks;
3. 增加analysis部分,对策略进行归纳分类,然后进行评测。
2025-04-17 17:40:15 +08:00

31 lines
1.1 KiB
JSON

{
"sites": [
"map"
],
"task_id": 7,
"require_login": true,
"storage_state": null,
"start_url": "https://www.openstreetmap.org",
"geolocation": null,
"intent_template": "Tell me the full address of all {{airport_type}} that are within a driving distance of {{radius}} to {{start}}",
"instantiation_dict": {
"airport_type": "international airports",
"start": "Carnegie Mellon University",
"radius": "50 km"
},
"intent": "Tell me the full address of all international airports that are within a driving distance of 50 km to Carnegie Mellon University",
"require_reset": false,
"eval": {
"eval_types": [
"string_match"
],
"reference_answers": {
"exact_match": "Pittsburgh International Airport, Southern Beltway, Findlay Township, Allegheny County, 15231, United States"
},
"reference_url": "",
"program_html": [],
"string_note": "",
"reference_answer_raw_annotation": "Pittsburgh International Airport People Movers, Airport Boulevard, Findlay Township, Allegheny County, Pennsylvania, 15231, United States"
},
"intent_template_id": 79
}